PoshCode Archive  Artifact [a4208d28e9]

Artifact a4208d28e926c6802de787101429839731c34781335848a8b379fb0419e36c0b:

  • File Get-FileEncoding.ps1 — part of check-in [6fb88d3112] at 2018-06-10 13:53:03 on branch trunk — Get-FileEncoding function determines encoding by looking at Byte Order Mark (BOM). (user: Chad Miller size: 1821)

# encoding: ascii
# api: powershell
# title: Get-FileEncoding
# description: Get-FileEncoding function determines encoding by looking at Byte Order Mark (BOM).
# version: 0.1
# type: script
# author: Chad Miller
# license: CC0
# function: Get-FileEncoding
# x-poshcode-id: 5290
# x-derived-from-id: 5291
# x-archived: 2015-03-04T03:23:37
# x-published: 2015-07-09T15:35:00
#
#
<#
.SYNOPSIS
Gets file encoding.
.DESCRIPTION
The Get-FileEncoding function determines encoding by looking at Byte Order Mark (BOM).
Based on port of C# code from http://www.west-wind.com/Weblog/posts/197245.aspx
.EXAMPLE
Get-ChildItem  *.ps1 | select FullName, @{n='Encoding';e={Get-FileEncoding $_.FullName}} | where {$_.Encoding -ne 'ASCII'}
This command gets ps1 files in current directory where encoding is not ASCII
.EXAMPLE
Get-ChildItem  *.ps1 | select FullName, @{n='Encoding';e={Get-FileEncoding $_.FullName}} | where {$_.Encoding -ne 'ASCII'} | foreach {(get-content $_.FullName) | set-content $_.FullName -Encoding ASCII}
Same as previous example but fixes encoding using set-content
#>
function Get-FileEncoding
{
    [CmdletBinding()] Param (
     [Parameter(Mandatory = $True, ValueFromPipelineByPropertyName = $True)] [string]$Path
    )

    [byte[]]$byte = get-content -Encoding byte -ReadCount 4 -TotalCount 4 -Path $Path

    if ( $byte[0] -eq 0xef -and $byte[1] -eq 0xbb -and $byte[2] -eq 0xbf )
    { Write-Output 'UTF8' }
    elseif ($byte[0] -eq 0xfe -and $byte[1] -eq 0xff)
    { Write-Output 'Unicode' }
    elseif ($byte[0] -eq 0 -and $byte[1] -eq 0 -and $byte[2] -eq 0xfe -and $byte[3] -eq 0xff)
    { Write-Output 'UTF32' }
    elseif ($byte[0] -eq 0x2b -and $byte[1] -eq 0x2f -and $byte[2] -eq 0x76)
    { Write-Output 'UTF7'}
    else
    { Write-Output 'ASCII' }
}